matula

and it seems... fine? SO MANY comments, but that seems pretty standard for LLM code these days.

I can prompt a fix or a new feature, have it coded in a couple of minutes, and I have enough domain knowledge to look at a diff and understand what's happening pretty quickly. It is ABSOLUTELY faster. And if Claude goes down, I could easily keep working.

The program director would literally hit a button and it would create the playlist for the week. The traffic department (ads) would have all the commercials also automatically placed within the list. Then there'd be a document to send to the on-air talent that showed what song was just played and what was coming up, and how long the break needed to be, and sometimes a script. At the time, quite a few got faxed to people and some did get emails... and the "DJ" would record their bits, set to the exact timing, and send them over an ISDN line. There was also some rudimentary STT (Dragon?) that transcribed the audio and was computer analyzed to make sure no cursing happened.

The PD would do some spot-checking, but I doubt he personally examined all 120+ hours of programming. And this was 2005.

I guess having a human voice did make it "feel" better? And the DJs did have some breaks that were unscripted, so their personality could come through. Even the best AI voices still don't have that.

So is this "slop" simply because it's written by an LLM, even if the output is solid? Would it NOT be slop if it was worse code, but written fully manually? Honestly, I'm not sure I know the answer.

I saved them locally and changed the reference, and it worked perfectly.

This is an under-appreciated aspect of Flash's popularity, and probably a reason why Animate didn't have the same appeal. A kid could get a "free" cracked copy and make fun things.... and maybe not help Adobe/Macromedia's bottom-line, it DID help the general ecosystem.

Rive seems fine, but monthly subscriptions need to die in a fire. I'm not going to pay $10/month to allow me to build some stupid animation idea I have every few months. There are a few, like GameMaker, that do one-time pricing... but even that doesn't scratch the same itch Flash did for me.

Yeah, screw those people. I count myself as lucky that I've only worked with 1 person who was seriously CRITICAL of the way other's worked... beyond just code quality. However, I always enjoyed a good discussion about the various differences in how people worked, as long as they could accept there's no "right" way. That's what the article brought up for me, and I wonder how much that happens these days.

One of my fondest memories was sitting around with a few other devs after work, and one had started learning Go pretty soon after its public release... and he would show us some new, cool thing he was playing around with. Of course those kind of organic things stopped with remote work, and I wonder how much THAT has played into the loss of identity?

Klondike solitaire game using Godot. The goal is to better understand Godot's inner workings, and not using any LLMs... outside of whatever Google searches automatically popup when I have questions.

Secondarily, decompiling the DuckTails Gameboy ROM with PHP... then seeing about using PHP to create a GameBoy game. For no reason than to see if it can be done.

No need for hacks, just better managers

Basically combining some game asset tools into one.

A (so far) simple AI assistant to provide help if you're moving with your pets to a different country. I've got a vector db with some US travel documents embedded, parse the question/prompt, and add the relevant context to a standard LLM request.

It also parses the question/prompt and stores move and pet details, so later questions will have context.

Eventually, the idea is to have a full tracker and reminder system... so deadlines, appointments, and documentation can be stored and referenced in a single place.

The current FeedLand gets close, and is nice for reading, but there's not a huge "social" aspect to it.

I feel no shame in doing the later. I've also learned enough about LLMs that I know how to write that CLAUDE.md so it sticks to best practices. YMMV.

But there is a "sweet spot" where it's amazing, specifically highly targeted tasks with a specific context. I wanted a simple media converter app that tied into ffmpeg, and I didn't want to install any of the spammy or bloated options I found... so I got Claude to build one. It took about 30 minutes and works great.

I also asked it to update some legacy project, and it fell down a testing a loop where it failed to understand the testing database was missing. Had I not had years of knowledge, I would've looked at the output and suggestions Claude was giving and spent hours on it... but it was a simple command that fixed it. As with all new tech, your milage will vary.

I think the same ideas can be applied to any hobby/job/industry. Picasso first learned how to paint a realistic apple... Wozniak spent years making calculators ... and I'm sure there are modern plumbing techniques created by someone who spent years learning the traditional techniques and decided to try something better. (Are there any famous, non-video game plumbers? There should be.)

Ignore the haters and copy other people's stuff.

The biggest issue is having the Ollama models hardcoded to Qwen3 and Llama 3.1. I imagine most Ollama users have their favorites, and probably vary quite a bit. My main model is usually Gemma 3 12B, which does support images.

It would be a nice feature to have a custom config on the Ollama settings page, save those to Chrome storage, and use that in the 'getAvailableModels' method, along with the hardcoded models.

Speaking of motte-and-bailey. But I actually disagree with the article's "what should you focus on". If you're a public-facing product, your focus should be on making something the user wants to use, and WILL use. And if your tech stack takes 30 seconds to boot up, that's probably not the case. However, if you spend much of your time trying eek out an extra millisecond of performance, that's also not focusing on the right thing (disclaimer: obviously if you have a successful, proven product/app already, performance gains are a good focus).

It's all about balance. Of course on HN people are going to debate microsecond optimizations, and this is perfect place to do so. But every so often, a post like this pops up as semi-rage bait, but mostly to reset some thinking. This post is simplistic, but that's what gets attention.

I think gaming is good example that illustrates a lot of this. The purpose of games is to appeal to others, and to actually get played. And there are SO many examples of very popular games built on slow, non-performant technologies because that's what the developer knew or could pick up easily. Somewhere else in this thread there is a mention of Minecraft. There are also games like Undertale, or even the most popular game last year Balatro. Those devs didn't build the games focusing on "performance", they made them focusing on playability.

IMHO, if we want to fix our education system, we need to cut the ties between funding and property values. Also, Democrats in office should probably get over the hard-line "no vouchers" position. With vouchers, they could also increase schools' funding to give them a better chance at competing. Of course, Republicans won't allow for the increased funding or "robin hood" funding. So yeah... we're screwed.